Fast Multi-Objective Optimization of Magnetic Shield Shape by Combining Auto-Encoder and Level-Set Method

Kanae Oda; Ryota Kawamata; Shinji Wakao; Noboru Murata

doi:10.1109/TMAG.2021.3074123

Fast Multi-Objective Optimization of Magnetic Shield Shape by Combining Auto-Encoder and Level-Set Method

Kanae Oda, Ryota Kawamata, Shinji Wakao, Noboru Murata

School of Advanced Science and Engineering

Research output: Contribution to journal › Article › peer-review

5 Citations (Scopus)

Abstract

We proposed a new multi-objective optimization approach combining both gradient calculation in actual high-dimensional design space and that in a low-dimensional latent space that is an appropriately compressed design space with Auto-Encoder. The proposed approach enables us to quickly and precisely search for more global pareto solution group in multi-objective optimization by using the optimization results in the low-dimensional space as the initial value of the gradient calculation in the actual design space.

Original language	English
Article number	9408617
Journal	IEEE Transactions on Magnetics
Volume	57
Issue number	7
DOIs	https://doi.org/10.1109/TMAG.2021.3074123
Publication status	Published - 2021 Jul

Keywords

Auto-encoder (AE)
latent variables
level-set method
multi-objective optimization
pareto solutions

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Electrical and Electronic Engineering

Access to Document

10.1109/TMAG.2021.3074123

Cite this

@article{676be6a6d7f247b387efa63ea3b1fd4c,

title = "Fast Multi-Objective Optimization of Magnetic Shield Shape by Combining Auto-Encoder and Level-Set Method",

abstract = "We proposed a new multi-objective optimization approach combining both gradient calculation in actual high-dimensional design space and that in a low-dimensional latent space that is an appropriately compressed design space with Auto-Encoder. The proposed approach enables us to quickly and precisely search for more global pareto solution group in multi-objective optimization by using the optimization results in the low-dimensional space as the initial value of the gradient calculation in the actual design space.",

keywords = "Auto-encoder (AE), latent variables, level-set method, multi-objective optimization, pareto solutions",

author = "Kanae Oda and Ryota Kawamata and Shinji Wakao and Noboru Murata",

note = "Funding Information: ACKNOWLEDGMENT This work was supported in part by JSPS KAKENHI under Grant 19H02132. Publisher Copyright: {\textcopyright} 1965-2012 IEEE.",

year = "2021",

month = jul,

doi = "10.1109/TMAG.2021.3074123",

language = "English",

volume = "57",

journal = "IEEE Transactions on Magnetics",

issn = "0018-9464",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "7",

}

TY - JOUR

T1 - Fast Multi-Objective Optimization of Magnetic Shield Shape by Combining Auto-Encoder and Level-Set Method

AU - Oda, Kanae

AU - Kawamata, Ryota

AU - Wakao, Shinji

AU - Murata, Noboru

PY - 2021/7

Y1 - 2021/7

N2 - We proposed a new multi-objective optimization approach combining both gradient calculation in actual high-dimensional design space and that in a low-dimensional latent space that is an appropriately compressed design space with Auto-Encoder. The proposed approach enables us to quickly and precisely search for more global pareto solution group in multi-objective optimization by using the optimization results in the low-dimensional space as the initial value of the gradient calculation in the actual design space.

AB - We proposed a new multi-objective optimization approach combining both gradient calculation in actual high-dimensional design space and that in a low-dimensional latent space that is an appropriately compressed design space with Auto-Encoder. The proposed approach enables us to quickly and precisely search for more global pareto solution group in multi-objective optimization by using the optimization results in the low-dimensional space as the initial value of the gradient calculation in the actual design space.

KW - Auto-encoder (AE)

KW - latent variables

KW - level-set method

KW - multi-objective optimization

KW - pareto solutions

UR - http://www.scopus.com/inward/record.url?scp=85104675667&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85104675667&partnerID=8YFLogxK

U2 - 10.1109/TMAG.2021.3074123

DO - 10.1109/TMAG.2021.3074123

M3 - Article

AN - SCOPUS:85104675667

SN - 0018-9464

VL - 57

JO - IEEE Transactions on Magnetics

JF - IEEE Transactions on Magnetics

IS - 7

M1 - 9408617

ER -

Fast Multi-Objective Optimization of Magnetic Shield Shape by Combining Auto-Encoder and Level-Set Method

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this